Layer-Wise PBF Process Data Analysis for Stable Additive Manufacturing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The powder bed fusion (PBF) additive manufacturing process faces challenges such as irregular heat characteristics, equipment-specific difficulties, and the need for extensive trial and error to optimize the process, with errors often going undetected until completion, leading to inefficiencies and increased costs in quality assurance.
Innovation Solution
A data-based system that collects and classifies data by layer, determines output success or failure, and analyzes process variables to optimize the PBF process, providing real-time monitoring and recommendations for process settings based on successful data patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If trial and error method is used to optimize PBF process, then process optimization may be achieved, but time consumption and cost increase significantly
Solution Approach 1:
The system performs preliminary actions by collecting and analyzing process data before actual manufacturing optimization is needed. It pre-establishes the relationships between process parameters and output quality through data collection from sensors and logs, enabling predictive optimization without requiring time-consuming trial and error during production
Solution Approach 2:
The system implements continuous feedback by collecting process data from sensors and equipment logs, analyzing the relationships between process variables and output quality, and using this feedback to guide process optimization. This closed-loop approach replaces random trial and error with data-driven iterative improvement
2Measurement precision
If monitoring system is established to check output status in real time, then quality checking is enabled, but it does not influence output preparation step and has limitations to preventing problems
Solution Approach 1:
The system extends monitoring from merely checking output status to collecting and analyzing data from the output preparation step as well. By examining process data before and during manufacturing, it can predict potential quality issues and provide optimization recommendations that prevent problems rather than just detecting them
Solution Approach 2:
The system creates a comprehensive feedback loop that connects output quality data with process parameter data. This enables the system to identify which process variables influenced quality outcomes and provide actionable feedback to optimize both preparation and execution phases, enhancing problem prevention capability
3Productivity
If data collection and analysis system is implemented, then trial and error is reduced and output stability is enhanced, but system complexity increases
Solution Approach 1:
The system achieves multi-functionality by combining data collection from multiple sources (sensors, equipment logs), data storage, data analysis, and optimization recommendation generation into a single integrated system. This universal approach handles various data types and analysis tasks without requiring separate specialized systems for each function
Solution Approach 2:
The system introduces a data analysis unit as an intermediary between raw process data and optimization decisions. This intermediary component processes and interprets complex multi-source data, transforming it into actionable optimization recommendations that improve output stability without requiring direct complex interactions between all system components
Data Source
AI summary
Provided are a system and a method for optimizing a process on the basis of data collected in a powder bed fusion (PBF) additive manufacturing process. A system for optimizing an additive manufacturing process, according to an embodiment of the present invention, comprises: a data collection unit for classifying, by layer, data on process variables collected during an output preparation step and an output step of a PBF additive manufacturing process; a storage unit for storing the data classified by layer by means of the data collection unit; a classification unit for determining whether output is successful for each layer; and an analysis unit for analyzing the process variables for process optimization on the basis of the result of determining whether output is successful for each layer. Therefore, data generated during the output preparation step and the output step of the PBF additive manufacturing process are collected and accumulated, and guiding for optimizing the output step is performed on the basis of the collected and accumulated data, and thus output trial and error can be reduced and output stability of a portion dependent on equipment status can be enhanced.